AI model
z-ai/glm-5
Z.ai: GLM 5 is a 204,800-token model served on Composite at $0.750 per million tokens in and $2.40 per million tokens out. Ranked #18 of 179 models by traffic on Composite over the last 30 days, taking 0.84% of tokens and 0.3% of requests (this model and its routing variants). Measured on Composite, 99.0% of its last 100 requests on Composite succeeded, the typical first token arrives in 13047 ms, output runs at about 171.0 tokens per second.
Try in Playground| Model ID | z-ai/glm-5 |
|---|---|
| Provider | cv11 |
| Context window | 204,800 tokens |
| Accepts | text |
| Returns | text |
| Input price | $0.750 per million tokens |
| Output price | $2.40 per million tokens |
| Prompt caching | Supported — cached input is billed at the provider's cache rate, on credits and plans alike |
| Moderated | No |
| Cost on a monthly plan | About 6.7 plan credits per typical call (8k in, 1k out) |
| Routing endpoints | 10 (base plus 9 routing variants) |
Make a Composite API key and type z-ai/glm-5 as the model name. JanitorAI takes the full URL https://composite.lucidity.sh/v1/chat/completions; SillyTavern, ChubAI, Agnai and RisuAI take https://composite.lucidity.sh/v1. It runs on credits, a plan, or your own provider key.
JanitorAI setup · SillyTavern setup · Best Janitor AI proxies compared
#18 of 179
0.84% of tokens and 0.3% of requests over 30 days, including routing variants.
99.0%
Across the last 100 requests Composite served for this model.
13047 ms
Median across the same sample.
171.0 tok/s
Median generation rate after the first token.
63.8%
Share of prompt tokens served from the provider's cache over 7 days.
The same model behind 9 alternative endpoints. Call the id directly to pin a route; the base id above picks for you.
| Route | Model ID | Provider | Price |
|---|---|---|---|
| Normal | z-ai/glm-5-normal |
cv11 | $1.25 per million tokens input · $4.00 per million tokens output |
| Normal + cheapThink | z-ai/glm-5-normal:cheapThink |
cv11 | $1.25 per million tokens input · $4.00 per million tokens output |
| Cheapest provider | z-ai/glm-5:cheapest-provider |
StreamLake | $0.750 per million tokens input · $2.40 per million tokens output |
| Cheapest provider + cheapThink | z-ai/glm-5:cheapest-provider:cheapThink |
StreamLake | $0.750 per million tokens input · $2.40 per million tokens output |
| cheapThink | z-ai/glm-5:cheapThink |
cv11 | $0.750 per million tokens input · $2.40 per million tokens output |
| Fast | z-ai/glm-5:fast |
StreamLake | $0.750 per million tokens input · $2.40 per million tokens output |
| Fast + cheapThink | z-ai/glm-5:fast:cheapThink |
StreamLake | $0.750 per million tokens input · $2.40 per million tokens output |
| Quality | z-ai/glm-5:quality |
SiliconFlow | $1.19 per million tokens input · $3.19 per million tokens output |
| Quality + cheapThink | z-ai/glm-5:quality:cheapThink |
SiliconFlow | $1.19 per million tokens input · $3.19 per million tokens output |
$0.750 per million tokens input · $2.40 per million tokens output
Credits pay the provider’s price plus 25%; cache hits cost less.
On a monthly plan, a typical call (8k tokens in, 1k out) uses about 6.7 plan credits, at the provider's own price.
cv11
GLM models balance strong instruction-following with competitive pricing, a reasonable middle ground for most roleplay setups.
With a 204,800-token context window, it can hold a long-running roleplay or a full lorebook in memory without losing earlier plot details, so it suits multi-session campaigns and character cards with heavy backstory.
It sits in the mid-range on price, a reasonable pick for regular roleplay use without going for the cheapest option available.
GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...
Supplied by cv11, not written by Composite.
Z.ai: GLM 5.3 FlashX Legal (Drafted) · Z.ai: GLM 5.3 Prime (Drafted) · Z.ai: GLM 5.3 FlashX (Drafted)